HIS-based Kaplan-Meier plots--a single source approach for documenting and reusing routine survival information

Clinical data for paediatric research: the Swiss approach : Proceedings of the National Symposium in Bern, Switzerland, Dec 5-6, 2019

BACKGROUND AND PURPOSE

Continuous improvement of health and healthcare system is hampered by inefficient processes of generating new evidence, particularly in the case of rare diseases and paediatrics. Currently, most evidence is generated through specific research projects, which typically require extra encounters with patients, are costly and entail long delays between the recognition of specific needs in healthcare and the generation of necessary evidence to address those needs. The Swiss Personalised Health Network (SPHN) aims to improve the use of data obtained during routine healthcare encounters by harmonizing data across Switzerland and facilitating accessibility for research. The project "Harmonising the collection of health-related data and biospecimens in paediatric hospitals throughout Switzerland (SwissPedData)" was an infrastructure development project funded by the SPHN, which aimed to identify and describe available data on child health in Switzerland and to agree on a standardised core dataset for electronic health records across all paediatric teaching hospitals. Here, we describe the results of a two-day symposium that aimed to summarise what had been achieved in the SwissPedData project, to put it in an international context, and to discuss the next steps for a sustainable future. The target audience included clinicians and researchers who produce and use health-related data on children in Switzerland.

KEY HIGHLIGHTS

The symposium consisted of state-of-the-art lectures from national and international keynote speakers, workshops and plenary discussions. This manuscript summarises the talks and discussions in four sections: (I) a description of the Swiss Personalized Health Network and the results of the SwissPedData project; (II) examples of similar initiatives from other countries; (III) an overview of existing health-related datasets and projects in Switzerland; and (IV) a summary of the lessons learned and future prospective from workshops and plenary discussions.

IMPLICATIONS

Streamlined processes linking initial collection of information during routine healthcare encounters, standardised recording of this information in electronic health records and fast accessibility for research are essential to accelerate research in child health and make it affordable. Ongoing projects prove that this is feasible in Switzerland and elsewhere. International collaboration is vital to success. The next steps include the implementation of the SwissPedData core dataset in the clinical information systems of Swiss hospitals, the use of this data to address priority research questions, and the acquisition of sustainable funding to support a slim central infrastructure and local support in each hospital. This will lay the foundation for a national paediatric learning health system in Switzerland.

Core Data Elements in Acute Myeloid Leukemia: A Unified Medical Language System-Based Semantic Analysis and Experts' Review

Background

For cancer domains such as acute myeloid leukemia (AML), a large set of data elements is obtained from different institutions with heterogeneous data definitions within one patient course. The lack of clinical data harmonization impedes cross-institutional electronic data exchange and future meta-analyses.

Objective

This study aimed to identify and harmonize a semantic core of common data elements (CDEs) in clinical routine and research documentation, based on a systematic metadata analysis of existing documentation models.

Methods

Lists of relevant data items were collected and reviewed by hematologists from two university hospitals regarding routine documentation and several case report forms of clinical trials for AML. In addition, existing registries and international recommendations were included. Data items were coded to medical concepts via the Unified Medical Language System (UMLS) by a physician and reviewed by another physician. On the basis of the coded concepts, the data sources were analyzed for concept overlaps and identification of most frequent concepts. The most frequent concepts were then implemented as data elements in the standardized format of the Operational Data Model by the Clinical Data Interchange Standards Consortium.

Results

A total of 3265 medical concepts were identified, of which 1414 were unique. Among the 1414 unique medical concepts, the 50 most frequent ones cover 26.98% of all concept occurrences within the collected AML documentation. The top 100 concepts represent 39.48% of all concepts’ occurrences. Implementation of CDEs is available on a European research infrastructure and can be downloaded in different formats for reuse in different electronic data capture systems.

Conclusions

Information management is a complex process for research-intense disease entities as AML that is associated with a large set of lab-based diagnostics and different treatment options. Our systematic UMLS-based analysis revealed the existence of a core data set and an exemplary reusable implementation for harmonized data capture is available on an established metadata repository.

Combination possibility and deep learning model as clinical decision-aided approach for prostate cancer

This study aims to introduce as proof of concept a combination model for classification of prostate cancer using deep learning approaches. We utilized patients with prostate cancer who underwent surgical treatment representing the various conditions of disease progression. All possible combinations of significant variables from logistic regression and correlation analyses were determined from study data sets. The combination possibility and deep learning model was developed to predict these combinations that represented clinically meaningful patient's subgroups. The observed relative frequencies of different tumor stages and Gleason score Gls changes from biopsy to prostatectomy were available for each group. Deep learning models and seven machine learning approaches were compared for the classification performance of Gleason score changes and pT2 stage. Deep models achieved the highest F1 scores by pT2 tumors (0.849) and Gls change (0.574). Combination possibility and deep learning model is a useful decision-aided tool for prostate cancer and to group patients with prostate cancer into clinically meaningful groups.

Common data elements for secondary use of electronic health record data for clinical trial execution and serious adverse event reporting

BACKGROUND

Data capture is one of the most expensive phases during the conduct of a clinical trial and the increasing use of electronic health records (EHR) offers significant savings to clinical research. To facilitate these secondary uses of routinely collected patient data, it is beneficial to know what data elements are captured in clinical trials. Therefore our aim here is to determine the most commonly used data elements in clinical trials and their availability in hospital EHR systems.

METHODS

Case report forms for 23 clinical trials in differing disease areas were analyzed. Through an iterative and consensus-based process of medical informatics professionals from academia and trial experts from the European pharmaceutical industry, data elements were compiled for all disease areas and with special focus on the reporting of adverse events. Afterwards, data elements were identified and statistics acquired from hospital sites providing data to the EHR4CR project.

RESULTS

The analysis identified 133 unique data elements. Fifty elements were congruent with a published data inventory for patient recruitment and 83 new elements were identified for clinical trial execution, including adverse event reporting. Demographic and laboratory elements lead the list of available elements in hospitals EHR systems. For the reporting of serious adverse events only very few elements could be identified in the patient records.

CONCLUSIONS

Common data elements in clinical trials have been identified and their availability in hospital systems elucidated. Several elements, often those related to reimbursement, are frequently available whereas more specialized elements are ranked at the bottom of the data inventory list. Hospitals that want to obtain the benefits of reusing data for research from their EHR are now able to prioritize their efforts based on this common data element list.

Current applications and future directions for the CDISC Operational Data Model standard: A methodological review

INTRODUCTION

In order to further advance research and development on the Clinical Data Interchange Standards Consortium (CDISC) Operational Data Model (ODM) standard, the existing research must be well understood. This paper presents a methodological review of the ODM literature. Specifically, it develops a classification schema to categorize the ODM literature according to how the standard has been applied within the clinical research data lifecycle. This paper suggests areas for future research and development that address ODM's limitations and capitalize on its strengths to support new trends in clinical research informatics.

METHODS

A systematic scan of the following databases was performed: (1) ABI/Inform, (2) ACM Digital, (3) AIS eLibrary, (4) Europe Central PubMed, (5) Google Scholar, (5) IEEE Xplore, (7) PubMed, and (8) ScienceDirect. A Web of Science citation analysis was also performed. The search term used on all databases was "CDISC ODM." The two primary inclusion criteria were: (1) the research must examine the use of ODM as an information system solution component, or (2) the research must critically evaluate ODM against a stated solution usage scenario. Out of 2686 articles identified, 266 were included in a title level review, resulting in 183 articles. An abstract review followed, resulting in 121 remaining articles; and after a full text scan 69 articles met the inclusion criteria.

RESULTS

As the demand for interoperability has increased, ODM has shown remarkable flexibility and has been extended to cover a broad range of data and metadata requirements that reach well beyond ODM's original use cases. This flexibility has yielded research literature that covers a diverse array of topic areas. A classification schema reflecting the use of ODM within the clinical research data lifecycle was created to provide a categorized and consolidated view of the ODM literature. The elements of the framework include: (1) EDC (Electronic Data Capture) and EHR (Electronic Health Record) infrastructure; (2) planning; (3) data collection; (4) data tabulations and analysis; and (5) study archival. The analysis reviews the strengths and limitations of ODM as a solution component within each section of the classification schema. This paper also identifies opportunities for future ODM research and development, including improved mechanisms for semantic alignment with external terminologies, better representation of the CDISC standards used end-to-end across the clinical research data lifecycle, improved support for real-time data exchange, the use of EHRs for research, and the inclusion of a complete study design.

CONCLUSIONS

ODM is being used in ways not originally anticipated, and covers a diverse array of use cases across the clinical research data lifecycle. ODM has been used as much as a study metadata standard as it has for data exchange. A significant portion of the literature addresses integrating EHR and clinical research data. The simplicity and readability of ODM has likely contributed to its success and broad implementation as a data and metadata standard. Keeping the core ODM model focused on the most fundamental use cases, while using extensions to handle edge cases, has kept the standard easy for developers to learn and use.

Ontology-based data integration between clinical and research systems

Data from the electronic medical record comprise numerous structured but uncoded ele-ments, which are not linked to standard terminologies. Reuse of such data for secondary research purposes has gained in importance recently. However, the identification of rele-vant data elements and the creation of database jobs for extraction, transformation and loading (ETL) are challenging: With current methods such as data warehousing, it is not feasible to efficiently maintain and reuse semantically complex data extraction and trans-formation routines. We present an ontology-supported approach to overcome this challenge by making use of abstraction: Instead of defining ETL procedures at the database level, we use ontologies to organize and describe the medical concepts of both the source system and the target system. Instead of using unique, specifically developed SQL statements or ETL jobs, we define declarative transformation rules within ontologies and illustrate how these constructs can then be used to automatically generate SQL code to perform the desired ETL procedures. This demonstrates how a suitable level of abstraction may not only aid the interpretation of clinical data, but can also foster the reutilization of methods for un-locking it.

Does single-source create an added value? Evaluating the impact of introducing x4T into the clinical routine on workflow modifications, data quality and cost-benefit

OBJECTIVES

The first objective of this study is to evaluate the impact of integrating a single-source system into the routine patient care documentation workflow with respect to process modifications, data quality and execution times in patient care as well as research documentation. The second one is to evaluate whether it is cost-efficient using a single-source system in terms of achieved savings in documentation expenditures.

METHODS

We analyzed the documentation workflow of routine patient care and research documentation in the medical field of pruritus to identify redundant and error-prone process steps. Based on this, we established a novel documentation workflow including the x4T (exchange for Trials) system to connect hospital information systems with electronic data capture systems for the exchange of study data. To evaluate the workflow modifications, we performed a before/after analysis as well as a time-motion study. Data quality was assessed by measuring completeness, correctness and concordance of previously and newly collected data. A cost-benefit analysis was conducted to estimate the savings using x4T per collected data element and the additional costs for introducing x4T.

RESULTS

The documentation workflow of patient care as well as clinical research was modified due to the introduction of the x4T system. After x4T implementation and workflow modifications, half of the redundant and error-prone process steps were eliminated. The generic x4T system allows direct transfer of routinely collected health care data into the x4T research database and avoids manual transcription steps. Since x4T has been introduced in March 2012, the number of included patients has increased by about 1000 per year. The average entire documentation time per patient visit has been significantly decreased by 70.1% (from 1116±185 to 334±83 s). After the introduction of the x4T system and associated workflow changes, the completeness of mandatory data elements raised from 82.2% to 100%. In case of the pruritus research study, the additional costs for introducing the x4T system are €434.01 and the savings are 0.48ct per collected data element. So, with the assumption of a 5-year runtime and 82 collected data elements per patient, the amount of documented patients has to be higher than 1102 to create a benefit.

CONCLUSION

Introduction of the x4T system into the clinical and research documentation workflow can optimize the data collection workflow in both areas. Redundant and cumbersome process steps can be eliminated in the research documentation, with the result of reduced documentation times as well as increased data quality. The usage of the x4T system is especially worthwhile in a study with a large amount of collected data or a high number of included patients.

Multilingual Medical Data Models in ODM Format: A Novel Form-based Approach to Semantic Interoperability between Routine Healthcare and Clinical Research

BACKGROUND

Semantic interoperability between routine healthcare and clinical research is an unsolved issue, as information systems in the healthcare domain still use proprietary and site-specific data models. However, information exchange and data harmonization are essential for physicians and scientists if they want to collect and analyze data from different hospitals in order to build up registries and perform multicenter clinical trials. Consequently, there is a need for a standardized metadata exchange based on common data models. Currently this is mainly done by informatics experts instead of medical experts.

OBJECTIVES

We propose to enable physicians to exchange, rate, comment and discuss their own medical data models in a collaborative web-based repository of medical forms in a standardized format.

METHODS

Based on a comprehensive requirement analysis, a web-based portal for medical data models was specified. In this context, a data model is the technical specification (attributes, data types, value lists) of a medical form without any layout information. The CDISC Operational Data Model (ODM) was chosen as the appropriate format for the standardized representation of data models. The system was implemented with Ruby on Rails and applies web 2.0 technologies to provide a community based solution. Forms from different source systems - both routine care and clinical research - were converted into ODM format and uploaded into the portal.

RESULTS

A portal for medical data models based on ODM-files was implemented (http://www.medical-data-models.org). Physicians are able to upload, comment, rate and download medical data models. More than 250 forms with approximately 8000 items are provided in different views (overview and detailed presentation) and in multiple languages. For instance, the portal contains forms from clinical and research information systems.

CONCLUSION

The portal provides a system-independent repository for multilingual data models in ODM format which can be used by physicians. It serves as a platform for discussion and enables the exchange of multilingual medical data models in a standardized way.